From Visual Synthesis to Interactive Worlds:
Toward Production-Ready 3D Asset Generation

Jiafeng Wu^1,2*†  ·  Zhuofan Lou^1,3*†  ·  Jian Liu^1‡
Chunchao Guo⁴  ·  Dazhao Du¹  ·  Song Guo^1§

¹ The Hong Kong University of Science and Technology
² Huazhong University of Science and Technology  ·  ³ Sichuan University  ·  ⁴ Tencent

* Equal contribution  ·  † Work done during internship at HKUST  ·  ‡ Project lead  ·  § Corresponding author

✦ Production-Oriented 3D Generation Survey ✦

🧭 Taxonomy · 🗂 Data · 📦 Objects · 🧍 Characters · 🌍 Scenes · 📏 Evaluation · 🏭 Industry

News

• 🔥 [2026-04] v2.0: Introduces a production-ready two-dimensional taxonomy spanning asset tiers and pipeline stages, and expands the collection to data foundations, geometry, topology, appearance, rigging, scene assembly, evaluation, and industry systems.
• 📚 [2025-08] v1.0: Established the initial curated 3D AIGC paper collection, organized object, scene, and avatar methods under 3D-native, 2D-prior, and hybrid paradigms, and tracked surveys, datasets, talks, companies, and implementations.

Abstract

Three-dimensional content generation has progressed from producing isolated, visually plausible shapes to constructing structured assets that can be deployed in real-time interactive environments. This trajectory is driven by converging demands from game development, embodied AI, world simulation, digital twins, and spatial computing, all of which require 3D content that goes beyond surface appearance to satisfy engine-level constraints on topology, UV parameterization, physically based materials, skeletal rigging, and physics-aware scene layout. Despite rapid advances in generative modeling, a persistent gap separates the outputs of current methods from the production-ready standard expected by interactive applications. This survey addresses that gap by organizing the literature around the asset production pipeline rather than algorithmic families.

At a Glance

• 🧭 Organized by a production-ready, pipeline-first taxonomy rather than isolated algorithm families.
• 📦 Covers three asset tiers: general objects, characters and avatars, and scenes and environments.
• 🛠 Tracks the full asset workflow from data foundations through geometry, topology, appearance, rigging, and scene assembly.
• 📚 Consolidates methods, datasets, evaluation criteria, and industry references in one companion list.

---

Table of Contents

• 🧭 Survey Taxonomy
• 🗂 Data Foundations & Benchmarks
  • 📦 Object Datasets
  • 🧍 Character Datasets
  • 🌍 Scene Datasets
• 📦 General Objects & Props
  • 🧱 Geometry Generation
  • 🕸 Topology Generation
  • 🎨 Appearance Generation
• 🧍 Characters & Avatars
  • 🧬 Structural Priors
  • 👤 Full-Body Synthesis
  • 🙂 Head & Face Synthesis
  • 🦴 Rigging & Skinning
• 🌍 Scenes & Environments
  • 🧩 Layout Generation
  • 🏗 Scene Population & Asset Grounding
  • 🌐 World-Scale Generation
• 📏 Evaluation & Benchmarks
• 🏭 Industry & Companies
• 📝 Citation
• 🤝 Contributing
• 🙏 Acknowledgments
• 🗃 v1 Paper Collection
• ⭐ Star History

---

Survey Taxonomy

The survey is organized around a two-dimensional taxonomy:

• Horizontal axis (asset types): General Objects, Characters & Avatars, Scenes & Environments
• Vertical axis (pipeline stages): Data Foundations → Geometry → Topology → Appearance → Rigging → Scene Assembly

This structure mirrors the production pipeline used in game engines and interactive applications, enabling direct assessment of where each method fits within a deployment workflow.

---

Data Foundations & Benchmarks

Object Datasets

Character Datasets

Scene Datasets

---

General Objects & Props

Geometry Generation

Score Distillation (SDS)

Multi-View Reconstruction (MV)

GAN-based

VAE / AE

Direct 3D Diffusion

Feed-Forward (FF)

Latent Generative Models (LGM)

Part-Aware

---

Topology Generation

Indirect Methods (Post-hoc Remeshing)

Direct Methods -- Autoregressive

Direct Methods -- Diffusion

---

Appearance Generation

UV Unwrapping

Texture & PBR Material Generation

---

Characters & Avatars

Structural Priors

Full-Body Synthesis

Parametric Template

Implicit / Hybrid

GAN / Diffusion Generative

Feed-Forward / Real-Time

Head & Face Synthesis

Morphable + Neural

Mesh-Anchored Gaussians

Feed-Forward Reconstruction

Rendering & Animation

Rigging & Skinning

Note: TADA!, ChuPa, LAM, and HRAvatar also include rigging capabilities -- see above.

---

Scenes & Environments

Layout Generation

Scene Population & Asset Grounding

World-Scale Generation

---

Evaluation & Benchmarks

The survey identifies several complementary evaluation dimensions for production-ready 3D generation:

A key finding of this survey is that existing benchmarks systematically overestimate deployment readiness by focusing on geometric and appearance metrics while neglecting topology, UV/PBR, engine import, and other asset usability criteria required for interactive applications.

---

Industry & Companies

---

Citation

If you find this survey useful, please cite our paper:

@article{wu2026visual,
  title={From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation},
  author={Wu, Jiafeng and Lou, Zhuofan and Liu, Jian and Du, Dazhao and Guo, Chunchao and Guo, Song},
  journal={arXiv preprint arXiv:2604.23629},
  year={2026}
}

If you also use resources from the v1 collection, please additionally cite:

@article{liu2024comprehensive,
  title={A Comprehensive Survey on 3D Content Generation},
  author={Liu, Jian and Huang, Xiaoshui and Huang, Tianyu and Chen, Lu and Hou, Yuenan and Tang, Shixiang and Liu, Ziwei and Ouyang, Wanli and Zuo, Wangmeng and Jiang, Junjun and others},
  journal={arXiv preprint arXiv:2402.01166},
  year={2024}
}

---

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Note: Pull requests should target the v2 branch. The main branch preserves the original v1 awesome list.

---

Acknowledgments

This work was supported by The Hong Kong University of Science and Technology and Tencent.

---

v1 Paper Collection

The original awesome list curated is preserved on the main branch. It contains a broader collection of AIGC 3D papers organized by topic without the production-pipeline focus of v2.

---

Star History